hyper-exponential.com

How to do humans learn about values?

TLDR: Tan Zhi Xuan builds cooperative, theory-of-mind agents for safer AI, favoring human-like value learning and interpretable, model-based systems…

Jun 19 • Mykhaylo Filipenko

Thoughts on ASI - part 2: Giving up Control to AGI

TLDR: I believe that we have given up a lot of control to technology already and that this resulted in a net benefit for humanity. Giving up more…

Jun 2 • Mykhaylo Filipenko

May 2025

Interview with Agustin Covarrubias

TLDR: Agus runs Kairos. Kairos helps AI safety groups at university to be run efficiently. Kairos also runs SPAR - one of the best known AI safety…

May 9 • Mykhaylo Filipenko

April 2025

Thoughts on ASI - part 1: A spiritualist's view

TLDR: It's close to impossible to predict what awaits us "post singularity". Nevertheless, I try to lay out arguments that can give us hope to be…

Apr 24 • Mykhaylo Filipenko

1

Why are LLMs so Good at Generating Code?

An Interview with Georg Zoller

Apr 16 • Mykhaylo Filipenko

There is hope for humanity ..

.. in one screenshot

Apr 4 • Mykhaylo Filipenko

Some thoughts on alignment ..

.. actually human alignment

Apr 2 • Mykhaylo Filipenko

March 2025

Safe AI with Singular Learning Theory ..

.. an interview with Jesse Hoogland from Timaeus

Mar 20 • Mykhaylo Filipenko

February 2025

Can we have safer AI through certification?

An Interview with Jan Zawadzski from CertifAI

Feb 27 • Mykhaylo Filipenko

The right people at the right place ..

.. make the biggest difference

Feb 4 • Mykhaylo Filipenko

January 2025

About bets and choices ..

.. and how they affect our lives

Jan 28 • Mykhaylo Filipenko

1

Dr. Jobst Heitzig: AGI with non-optimizer and how to start an AI safety lab in Germany?

TLDR: Dr.

Jan 8 • Mykhaylo Filipenko